vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-05-08 01:41:37 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 3

Merge commit 'c945aaaef2' into concedo_experimental

Browse source 
# Conflicts:
#	.devops/cann.Dockerfile
#	.github/workflows/build.yml
#	.github/workflows/release.yml
#	README.md
#	common/CMakeLists.txt
#	common/chat.cpp
#	docs/function-calling.md
#	ggml/src/ggml-cann/aclnn_ops.cpp
#	ggml/src/ggml-cann/aclnn_ops.h
#	ggml/src/ggml-cann/common.h
#	ggml/src/ggml-cann/ggml-cann.cpp
#	models/templates/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16.jinja
#	scripts/sync_vendor.py
#	tests/CMakeLists.txt
#	tests/peg-parser/tests.h
#	tests/test-chat-peg-parser.cpp
#	tests/test-chat-template.cpp
#	tests/test-chat.cpp
#	tests/testing.h
#	tools/llama-bench/llama-bench.cpp
This commit is contained in:
Concedo 2026-01-17 10:24:03 +08:00
commit 8855a7f52b
23 changed files with 6659 additions and 3690 deletions
Download patch file Download diff file Expand all files Collapse all files

7
koboldcpp.py
View file

@ -8512,6 +8512,10 @@ def kcpp_main_process(launch_args, g_memory=None, gui_launcher=False):
except Exception:
print("Could not find Embedded llama.cpp UI.")
if args.mcpfile and isinstance(args.mcpfile, str):
threading.Thread(target=load_mcp_async, args=(args,), daemon=True).start()
time.sleep(0.2) # short delay to allow get_capabilities to work
# print enabled modules
caps = get_capabilities()
enabledmlist = []
@ -8561,9 +8565,6 @@ def kcpp_main_process(launch_args, g_memory=None, gui_launcher=False):
else:
endpoint_url = f"{httpsaffix}://{args.host}:{args.port}"
if args.mcpfile and isinstance(args.mcpfile, str):
threading.Thread(target=load_mcp_async, args=(args,), daemon=True).start()
if start_server:
if not args.remotetunnel:
print(f"Starting Kobold API on port {args.port} at {endpoint_url}/api/")